Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 226 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.6361. Min Act: -0.1700

Data Index: 1004896 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5735. Min Act: -0.1700

Data Index: 313817 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5421. Min Act: -0.1700

Data Index: 968630 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5735. Min Act: -0.1700

Data Index: 1211753 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5421. Min Act: -0.1700

Data Index: 634464 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5108. Min Act: -0.1700

Data Index: 380878 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1022508 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.4795. Min Act: -0.1700

Data Index: 222549 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5421. Min Act: -0.1700

Data Index: 793081 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5108. Min Act: -0.1700

Data Index: 267344 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5108. Min Act: -0.1700

Data Index: 432472 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.4795. Min Act: -0.1700

Data Index: 408565 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.4795. Min Act: -0.1700

Data Index: 139023 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5421. Min Act: -0.1700

Data Index: 590794 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.5108. Min Act: -0.1700

Data Index: 74683 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.4481. Min Act: -0.1700

Data Index: 250308 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.3854. Min Act: -0.1700

Data Index: 936454 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.3854. Min Act: -0.1700

Data Index: 525229 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.4795. Min Act: -0.1700

Data Index: 459084 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 3.6361. Min Range: -3.6361

Max Act: 3.4481. Min Act: -0.1700

Data Index: 989671 (C4 (Web Text))

Max Activating Token Index: 193